compact_array_of_strings_tuple_sketch< Allocator > Class Template Reference

Extended class of compact_tuple_sketch for array of strings. More...

#include <array_of_strings_sketch.hpp>

Inheritance diagram for compact_array_of_strings_tuple_sketch< Allocator >:

Public Member Functions
template<typename Sketch >
	compact_array_of_strings_tuple_sketch (const Sketch &sketch, bool ordered=true)
	Copy constructor.
template<typename SerDe = serde<Summary>>
void	serialize (std::ostream &os, const SerDe &sd=SerDe()) const
	This method serializes the sketch into a given stream in a binary form.
template<typename SerDe = serde<Summary>>
vector_bytes	serialize (unsigned header_size_bytes=0, const SerDe &sd=SerDe()) const
	This method serializes the sketch as a vector of bytes.
Public Member Functions inherited from compact_tuple_sketch< Summary, Allocator >
	compact_tuple_sketch (const Base &other, bool ordered)
	Copy constructor.
	compact_tuple_sketch (const compact_tuple_sketch &other)=default
	Copy constructor.
	compact_tuple_sketch (compact_tuple_sketch &&) noexcept
	Move constructor.
compact_tuple_sketch &	operator= (const compact_tuple_sketch &other)=default
	Copy assignment.
compact_tuple_sketch &	operator= (compact_tuple_sketch &&other)=default
	Move assignment.
	compact_tuple_sketch (const theta_sketch_alloc< AllocU64 > &other, const Summary &summary, bool ordered=true)
	Constructor from Theta sketch.
virtual Allocator	get_allocator () const
virtual bool	is_empty () const
virtual bool	is_ordered () const
virtual uint64_t	get_theta64 () const
virtual uint32_t	get_num_retained () const
virtual uint16_t	get_seed_hash () const
template<typename Predicate >
compact_tuple_sketch	filter (const Predicate &predicate) const
	Produces a Compact Tuple sketch from this sketch by applying a given predicate to each entry.
template<typename SerDe = serde<Summary>>
void	serialize (std::ostream &os, const SerDe &sd=SerDe()) const
	This method serializes the sketch into a given stream in a binary form.
template<typename SerDe = serde<Summary>>
vector_bytes	serialize (unsigned header_size_bytes=0, const SerDe &sd=SerDe()) const
	This method serializes the sketch as a vector of bytes.
virtual iterator	begin ()
	Iterator over entries in this sketch.
virtual iterator	end ()
	Iterator pointing past the valid range.
virtual const_iterator	begin () const
	Const iterator over entries in this sketch.
virtual const_iterator	end () const
	Const iterator pointing past the valid range.
Public Member Functions inherited from tuple_sketch< Summary, Allocator >
double	get_estimate () const
double	get_lower_bound (uint8_t num_std_devs, uint32_t num_subset_entries) const
	Returns the approximate lower error bound given a number of standard deviations over an arbitrary number of items stored in the sketch.
double	get_lower_bound (uint8_t num_std_devs) const
	Returns the approximate lower error bound given a number of standard deviations.
double	get_upper_bound (uint8_t num_std_devs, uint32_t num_subset_entries) const
	Returns the approximate upper error bound given a number of standard deviations over an arbitrary number of items stored in the sketch.
double	get_upper_bound (uint8_t num_std_devs) const
	Returns the approximate upper error bound given a number of standard deviations.
bool	is_estimation_mode () const
double	get_theta () const
string< Allocator >	to_string (bool print_items=false) const
	Provides a human-readable summary of this sketch as a string.

Static Public Member Functions
template<typename SerDe = default_array_of_strings_serde<Allocator>>
static compact_array_of_strings_tuple_sketch	deserialize (std::istream &is, uint64_t seed=DEFAULT_SEED, const SerDe &sd=SerDe(), const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given stream.
template<typename SerDe = default_array_of_strings_serde<Allocator>>
static compact_array_of_strings_tuple_sketch	deserialize (const void *bytes, size_t size, uint64_t seed=DEFAULT_SEED, const SerDe &sd=SerDe(), const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given array of bytes.
Static Public Member Functions inherited from compact_tuple_sketch< Summary, Allocator >
template<typename Sketch , typename Predicate >
static compact_tuple_sketch	filter (const Sketch &sketch, const Predicate &predicate)
	Produces a Compact Tuple sketch from a given sketch (Update or Compact) by applying a given predicate to each entry.
template<typename SerDe = serde<Summary>>
static compact_tuple_sketch	deserialize (std::istream &is, uint64_t seed=DEFAULT_SEED, const SerDe &sd=SerDe(), const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given stream.
template<typename SerDe = serde<Summary>>
static compact_tuple_sketch	deserialize (const void *bytes, size_t size, uint64_t seed=DEFAULT_SEED, const SerDe &sd=SerDe(), const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given array of bytes.

Additional Inherited Members
Protected Member Functions inherited from compact_tuple_sketch< Summary, Allocator >
template<typename SerDe , typename SS = Summary, typename std::enable_if< std::is_arithmetic< SS >::value, int >::type = 0>
size_t	get_serialized_size_summaries_bytes (const SerDe &sd) const
	Computes size needed to serialize summaries in the sketch.
template<typename SerDe , typename SS = Summary, typename std::enable_if<!std::is_arithmetic< SS >::value, int >::type = 0>
size_t	get_serialized_size_summaries_bytes (const SerDe &sd) const
	Computes size needed to serialize summaries in the sketch.

Detailed Description

template<typename Allocator = std::allocator<array_of_strings>>
class datasketches::compact_array_of_strings_tuple_sketch< Allocator >

Extended class of compact_tuple_sketch for array of strings.

Requirements:

• Array size must be <= 127.

UTF-8 compatibility: Serialized sketches are intended to be language and platform independent. Other implementations (Java, Go, Rust) enforce UTF-8 encoding for strings. This C++ implementation does not validate UTF-8; it is the caller's responsibility to ensure all strings are valid UTF-8 before calling update(). Non-UTF-8 strings may serialize successfully but will fail to deserialize in other language implementations.

Constructor & Destructor Documentation

compact_array_of_strings_tuple_sketch()

template<typename Allocator >

template<typename Sketch >

compact_array_of_strings_tuple_sketch	(	const Sketch &	sketch,
		bool	ordered = true
	)

Copy constructor.

Constructs a compact sketch from another sketch (update or compact)

Parameters

other	sketch to be constructed from
ordered	if true make the resulting sketch ordered

Member Function Documentation

deserialize() [1/2]

template<typename Allocator = std::allocator<array_of_strings>>

template<typename SerDe = default_array_of_strings_serde<Allocator>>

static compact_array_of_strings_tuple_sketch deserialize ( std::istream &  is, uint64_t  seed = DEFAULT_SEED, const SerDe &  sd = SerDe(), const Allocator &  allocator = Allocator()  )

static

This method deserializes a sketch from a given stream.

Parameters

is	input stream
seed	the seed for the hash function that was used to create the sketch
sd	instance of a SerDe
allocator	instance of an Allocator

Returns

an instance of the sketch

deserialize() [2/2]

template<typename Allocator = std::allocator<array_of_strings>>

template<typename SerDe = default_array_of_strings_serde<Allocator>>

static compact_array_of_strings_tuple_sketch deserialize ( const void *  bytes, size_t  size, uint64_t  seed = DEFAULT_SEED, const SerDe &  sd = SerDe(), const Allocator &  allocator = Allocator()  )

static

This method deserializes a sketch from a given array of bytes.

Parameters

bytes	pointer to the array of bytes
size	the size of the array
seed	the seed for the hash function that was used to create the sketch
sd	instance of a SerDe
allocator	instance of an Allocator

Returns

an instance of the sketch

serialize() [1/2]

template<typename Allocator = std::allocator<array_of_strings>>

template<typename SerDe = serde<Summary>>

void serialize	(	std::ostream &	os,
		const SerDe &	sd = SerDe()
	)		const

This method serializes the sketch into a given stream in a binary form.

Parameters

os	output stream
sd	instance of a SerDe

serialize() [2/2]

template<typename Allocator = std::allocator<array_of_strings>>

template<typename SerDe = serde<Summary>>

vector_bytes serialize	(	unsigned	header_size_bytes = 0,
		const SerDe &	sd = SerDe()
	)		const

This method serializes the sketch as a vector of bytes.

An optional header can be reserved in front of the sketch. It is a blank space of a given size. This header is used in Datasketches PostgreSQL extension.

Parameters

header_size_bytes	space to reserve in front of the sketch
sd	instance of a SerDe

Returns

serialized sketch as a vector of bytes

---

The documentation for this class was generated from the following files:

• tuple/include/array_of_strings_sketch.hpp
• tuple/include/array_of_strings_sketch_impl.hpp